Scientific equipment supplier KPM Analytics has developed an AI-based contaminant detection and product grading system for potatoes that targets processing challenges facing the F&B industry, such as foreign objects and inaccurate quality grading that reduces profits.

The SiftAI Smart Table equipment, marketed under the company’s brand Smart Vision Works, “precisely grades produce using sophisticated evaluation of bruises, rot and green,” notes the company.

According to the Potato Association of America, bruised potatoes cost processors money, including the price of additional labor required to sort out unusable crops and trim the salvageable ones. They must also replac the loss of usable material from trimming and sorting.

“We estimate that up to 20% of potatoes are typically diverted to the wrong value stream, reducing profitability and causing customer satisfaction issues,” says Christopher Bryant, president of the Smart Vision Works AI Division within KPM Analytics.

“A more accurate sorting system diverts less produce to less profitable uses and higher quality produce can command a higher price.”

The system includes cameras, AI software, a conveyor and automatic ejection mechanisms with dual drops (one for foreign material, one for culls) to ensure that only good-quality potatoes reach later processing stages.

Leveraging advanced AI

Food processors usually rely on methods like X-ray detection, metal detection, vision inspection systems and human inspectors to detect contaminants and ensure the food safety of their products. However, these methods pose certain challenges that the KPM Analytics system aims to overcome.

“The SiftAI Smart Table is trained with AI to automatically detect and remove foreign objects and sort products in a single pass. Unlike competing vision inspection systems, the new system uses advanced AI that is more accurate, allowing companies to inspect products and remove foreign materials at higher throughputs than ever before.”

According to the company, the AI used in the equipment was developed using the expertise of AI scientists and a decade of experience in food sorting applications.

“Unlike competitors that use optical scanners, the system takes a full digital image and runs it through a neural network. Users receive detailed data for analysis.”

The company claims its beta customers to have reported higher produce profit, fewer missed contaminants and lower labor costs.

Potato processor benefits

The Westborough, US-based firm says its AI-driven system addresses specific business and operational challenges potato processors face daily.

The system helps chip potato manufacturers avoid penalties (chargebacks) by “immediately” removing foreign materials from the process stream. It also helps pre-sort fresh pack potatoes to reduce potato volume through the facility.

In related news, scientists in the US recently tackled rots and moisture loss in Kalkaska potatoes by formulating a genetically engineered potato variety that nclick="updateothersitehits('Articlepage','External','OtherSitelink','AI-based potato contaminant detector targets bruises and rot to elevate profitability','AI-based potato contaminant detector targets bruises and rot to elevate profitability','343244','https://www.foodingredientsfirst.com/news/researchers-silence-sugars-in-genetically-engineered-potato-to-cut-browning-and-enhance-shelf-life.html', 'article','AI-based potato contaminant detector targets bruises and rot to elevate profitability');return no_reload();">minimize the off-color browning and caramelization to yield healthier, higher-quality potato chips with extended cold storage times.